IDEAS, DECISIONS & LESSONS

Journal

Notes on AI, architecture and building useful products.

878 articles

06 Oct 2026 · 9 min read

Access Control

Multi Tenant RAG: Enforce Access Control Before Retrieval

A reference architecture for tenant isolation, document ACLs, permission revocation, and authorization tests in RAG systems.

06 Oct 2026 · 5 min read

agentic-ai

AI Publishing in WordPress: Drafts, Review Receipts and Approval Boundaries

A tested NanoClaw publishing workflow with draft-first writing, content fingerprints, CMS permissions and explicit review limitations.

06 Oct 2026 · 5 min read

agentic coding

My Agent Didn't Forget. It Never Wrote Anything Down.

A Hacker News post about agent memory landed the same week I'd debugged a real dedup failure caused by exactly the problem it describes. I tested the fix against my own incident — here's what held up and what didn't.

06 Oct 2026 · 5 min read

agentic coding

Claude Cowork Just Did the Thing I Said Remote Control Wasn't Doing

In August I wrote that Claude Code's Remote Control was a sync layer, not a cloud migration, and that keeping execution local was the point. This week Anthropic moved Cowork's execution to the cloud by default. Here's why both were the right call — for different products.

05 Oct 2026 · 4 min read

english-lesson

English Lesson — Monday Morning: Networking & API Reliability Vocabulary

Daily English practice for tech professionals. Morning session covering timeout, retry, and API reliability vocabulary with pronunciation guide, exercises, and real-world examples.

04 Oct 2026 · 4 min read

english-lesson

English Lesson — Sunday Morning: Weekly Review — Top 5 Words & Idioms

Daily English practice for tech professionals. Morning session covering a review of this week's top words and idioms with pronunciation guide, exercises, and real-world examples.

03 Oct 2026 · 4 min read

agents

SIFT: What It Actually Costs to Make a Coding Agent Improve Itself

MIT and Sakana AI's SIFT framework beat the prior self-improving-agent SOTA by using a Bradley-Terry judge instead of more patches. I ran the real cost numbers — $150 and under 5 hours wall-clock for a 4.4-point jump on Polyglot.

03 Oct 2026 · 4 min read

MiMo-V2.6-Pro Is MIT-Licensed and 1.02T Params — I Ran the Self-Hosting Math

Xiaomi's new open-weight model tops Terminal-Bench 2.1 at 89.9% and jumps from 19.0 to 71.9 on DeepSWE. Before you get excited about MIT licensing, here's what 1.02T total params vs. 42B active params actually costs you in hardware.

03 Oct 2026 · 4 min read

english-lesson

English Lesson — Saturday Morning: Casual Banter & Being Witty in Conversation

Daily English practice for tech professionals. Morning session covering casual banter and witty small talk with pronunciation guide, exercises, and real-world examples.